Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 119466
    Prev
    Next
    INDEX
    Explanations

    Medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     racism
    -0.07
    χν
    -0.06
    -commercial
    -0.06
    stit
    -0.06
     '%
    -0.06
     persu
    -0.06
     feder
    -0.06
    .Query
    -0.06
     patents
    -0.06
    /music
    -0.06
    POSITIVE LOGITS
    azar
    0.07
    ок
    0.07
    Η
    0.07
    ibel
    0.07
    withstanding
    0.06
    aoke
    0.06
    _sections
    0.06
    なお
    0.06
    ippets
    0.06
    очного
    0.06
    Activations Density 0.094%

    No Known Activations